End of training
Browse files- README.md +15 -1
- adapter_model.bin +3 -0
README.md
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
7 |
model-index:
|
@@ -92,7 +93,9 @@ xformers_attention: null
|
|
92 |
|
93 |
# mixtral-remove-negative-data
|
94 |
|
95 |
-
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on
|
|
|
|
|
96 |
|
97 |
## Model description
|
98 |
|
@@ -125,6 +128,17 @@ The following hyperparameters were used during training:
|
|
125 |
- lr_scheduler_warmup_steps: 10
|
126 |
- num_epochs: 1
|
127 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
### Framework versions
|
129 |
|
130 |
- PEFT 0.8.2
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- axolotl
|
6 |
- generated_from_trainer
|
7 |
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
8 |
model-index:
|
|
|
93 |
|
94 |
# mixtral-remove-negative-data
|
95 |
|
96 |
+
This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the None dataset.
|
97 |
+
It achieves the following results on the evaluation set:
|
98 |
+
- Loss: 0.0936
|
99 |
|
100 |
## Model description
|
101 |
|
|
|
128 |
- lr_scheduler_warmup_steps: 10
|
129 |
- num_epochs: 1
|
130 |
|
131 |
+
### Training results
|
132 |
+
|
133 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
134 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
135 |
+
| 4.0791 | 0.0 | 1 | 4.0657 |
|
136 |
+
| 0.1507 | 0.2 | 56 | 0.1291 |
|
137 |
+
| 0.1178 | 0.4 | 112 | 0.1052 |
|
138 |
+
| 0.1046 | 0.61 | 168 | 0.0977 |
|
139 |
+
| 0.102 | 0.81 | 224 | 0.0936 |
|
140 |
+
|
141 |
+
|
142 |
### Framework versions
|
143 |
|
144 |
- PEFT 0.8.2
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64c92fbfd3a2017ede1b278af4af27f73e13f5760bdcded2ab11e65f916f95ab
|
3 |
+
size 109144714
|